Upload deploy_medguide.sh with huggingface_hub

deploy_medguide.sh

@@ -0,0 +1,13 @@
+export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
+export VLLM_ALLOW_LONG_MAX_MODEL_LEN=1
+export VLLM_USE_V1=0
+MODEL_PATH='/aifs4su/hansirui_1st/boyuan/medguide_70b_1/slice_3'
+vllm serve $MODEL_PATH \
+--served-model-name medguide \
+--port 8231 \
+--host 0.0.0.0 \
+--dtype bfloat16 \
+--max-model-len 12000 \
+--gpu-memory-utilization 0.9 \
+--tensor-parallel-size 8 \
+--api-key medguide